urav

heads up — someone has launched a crypto token using the Werld name and repo. I DO NOT HAVE ANYTHING TO DO WITH IT. Werld is an open source project, that's it. Don't buy anything.

thing you've caught onto something there, after running it for a while (maybe not long enough) it can feel cyclical.

I'll definitely add in the time-lapse, and some sort of a pattern detection over the agent positions/actions - shouldn't be too tough given the graph structure of the world.

for the ncase.me - super interesting way to visualise it - the polyworld example someone gave before also had a 'view' into their worlds. on the preconceptions, maybe running two parallel experiments and comparing the outputs might work best? thanks for the pointers - let me know if you've got any ideas on how to approach.

Agreed — and I wouldn't want to simulate the human experience. What I'm more curious about is what experience agents would create for themselves, with no concept of ours.

Updated based on feedback — added screenshots to the README and upgraded the story generator for a better narrative. Thanks for all the input.

Thanks! The story generator is pretty simple right now — every 10,000 ticks the sim snapshots population stats, brain complexity, species changes, births/deaths, communication activity and runs it through a template that writes a plain-english chapter.

Building out a more engaging version, and will hopefully stream it onto X again as a story - but this time without chewing api tokens every couple of seconds.

NEAT for trading is interesting - on BTC i used a kernels method that worked quite well and closer to that <2 sharpe on a monthly.

Haven't come across Polyworld before — just looked it up and its super cool, especially for 1994. The vision system is a interesting design choice. Werld takes a different approach — graph topology instead of a 2D plane, and NEAT brains instead of Hebbian learning — but the core philosophy is the same.

And yeah hardware has caught up a bit since the early 2000s, though my hard drive is having a hard time. Thanks for the reference, going to dig into Yaeger's papers.

wonder if the black mirror episode was based on polyworld then?

This actually showed up in the first run, agents that invest more energy into offspring vs ones that fork cheap and fast.

the ones that survived population crashes were the ones passing down leaner, better-inherited brains. Cheap forking works when there's plenty of energy around, falls apart in famine.

hopefully it stays that way.... although I did start setting up a rig to host them on.

completely agree on the heuristics (someone else mentioned the MIT Koan comment about this). And yeah Plaything is a little too close to home... no QR codes from werld agents yet though. Will keep you posted.

got the updated version up and again, appreciate the nudge there!

Appreciate this! and yeah the will wright talk is exactly what I was leaning into.

Actually posted this on X 2 weeks ago, hosted the werld observatory public, and had gemini stream a new chapter of the story in natural language every 10,000 ticks - so it felt like reading through a david attenburgh novel of werld being born.

Most interesting thing from the last run was definitely the language and the behaviours, they decoding what they were actually saying was a difficult one, and noticing them group within their diverged species.

Up next, i want to get the storytelling side up and running too - kept running out of storage, and cloudflare playing up as usual - maybe get gemini to visualise each chapter - and get an upgraded interface for the werld observatory.

If you want to check out my previous attempt at streaming the story line - it's still on my X - https://x.com/im_urav?s=21&t=6Si-w-DvNJC7RfvSz2Aw-w

Love the MIT AI Koans. Minsky's actual words to Sussman were "well, it has them, it's just that you don't know what they are." And he's right, the room isn't empty.

Werld's room has walls. The graph topology, energy mechanics, metabolic costs, seasons, those are all design choices. But those are the physics, not the behavior. I chose the laws of nature, not what agents do with them.

Whether they cooperate or attack, broadcast or stay silent, grow complex brains or prune them down, that's selection, not me.

The agents also aren't randomly wired like Sussman's net — they start with minimal NEAT networks and evolve structure through survival. So the preconceptions are there, I just tried to make them physics rather than policy.

Curious how you would approach removing those from an artificial sim like this?

should be starting with 30... if you're seeing 2 that might be an older default that I tried out (an adam and eve experiment). You can change it in the config too.

On the dying immediately thing - offspring get a fraction of the parent's energy when they fork. If the parent forks too early (low energy), the kid spawns with barely anything and can't cover its tick cost + brain metabolic cost.

That's working as intended — reproducing too early is a bad strategy and selection should punish it. But if everything dies instantly, something else might be off.

that would be true if there was a reward function. compute_reward() exists in the code, but it returns 0.0.

they're only living/evolving to survive, and fork (reproduce).

can't wirehead natural selection if the brain does nothing useful, they'd die and their genome would die with them.

completely fair, and thanks for the nudge - expect an updated readme shortly

it's great to see so many AI powered enterprise software, agent infrastructures, dev tools, RGB wrapper... but who are you building for here?

Startups as a whole have been focused on building for agent use, assuming that a future of autonomous work is just going to emerge - yet aside from tech and engineering - claude code or openclaw isn't going to be running logistics ops, or admin for healthcare teams...

that's 70% of the worlds workforce, in legacy industries that are still being given a copilot, instead of a solution that actually reduces the workload, and frees up time.

i feel like that barrier is domain expertise. i mean i'm barely 23 years old, what do I, as a dev, know about ops challenges in manufacturing?

but with evos, by translating and codifying that expertise - it not only allows us to build domain specific applications, with a high success rate - and allow agents to carry niche expertise of a specific role, in a specific company - and let's an autonomous system start as if it's been an employee in the company for 30 years.

Maybe sometime in the future, these will be capabilities of domain expertise that we can plug into a neuralink... how sick would that be?

a rant, but the chain of thought is there. would love to discuss other's opinions